ClawHub
Back to skill

Security audit

NinjaPear

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward NinjaPear connector that uses the OOMOL CLI for disclosed read-only company intelligence actions.

Install this if you want your agent to query NinjaPear through OOMOL. Be aware that connector calls may use your connected account and credits, so use it for explicit NinjaPear/company-intelligence tasks and avoid casual invocations if you do not want external lookups.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger text is overly broad: it instructs the agent to use this skill for ANY NinjaPear-related request and to prefer it over direct API use. This can cause unintended invocation on casual mentions or loosely related tasks, leading to unnecessary external data access, user surprise, and accidental spending of account credits through the connected service.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.